Training in progress, step 340, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e28928720afbfd431ec4a6381b22773b2e78102af9c1e41480a9554b7a5e4e
+oid sha256:1f71ccf5d1e38095d0550ef25eaf8142cfc6e91c44bbcd52a9b26ef54fd7f0de
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1055abafe6a0e6141e462e4a9d7c405c2ba30875112c901416cf3dd79cf92466
+oid sha256:2fa0b74037207edb69c5cb7e46115ced0b01214628bf235c30fc7fa7ba5c66cf
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9350673392e31b98858f6fe816923eae7f55b9f3f625f62a4fbef924f908709
+oid sha256:572dc22acc56b39f566c3fd3cffdea889adb8a7c20c07536c97592135eb24b9e
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07185e8ad02f9bc11c0bd4a82441f8a3bb2aaa16f696dfa0b75d528de14c8cf9
+oid sha256:ecc681d4faad785e373f4f3e510befc4a0dd5c362d6b35fce077246bbe11af20
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc99919da5a7742331644c92ad35399b61089cf3cf76c5e4355b2e567e5f74d4
+oid sha256:775af4447ea22c8fde6b9577374f0010f59aa5050c5eb44816a7c00e793e5d27
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 24.615384615384617,
+  "epoch": 26.153846153846153,
   "eval_steps": 40,
-  "global_step": 320,
+  "global_step": 340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,20 @@
       "eval_samples_per_second": 284.679,
       "eval_steps_per_second": 4.552,
       "step": 320
+    },
+    {
+      "epoch": 25.384615384615383,
+      "grad_norm": 0.412109375,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 9.2001,
+      "step": 330
+    },
+    {
+      "epoch": 26.153846153846153,
+      "grad_norm": 0.416015625,
+      "learning_rate": 8.626464421815919e-05,
+      "loss": 9.193,
+      "step": 340
     }
   ],
   "logging_steps": 10,
@@ -322,7 +336,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 130930735841280.0,
+  "total_flos": 139113906831360.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null